Web App Research Articles

Handpose Estimation Based Learning Academy for Improving Typing Efficiency by Using Mobile Technologies

This paper focuses on enhancing touch-typing skills through state-of-the-art deep learning technologies. It has been demonstrated that writing posture can be assessed using integrated keyboard detection and hand pose estimation in real-time browser environments. A unique dataset was created for training the object detection model to recognize individual keyboards. The object detection models were trained using various architectures and then assessed for both inference time and accuracy. In addition, a hand pose estimation was implemented to precisely recognize 21 knuckle points of the hand and compute their exact positions. In order to implement object detection and hand pose estimation, a stream transmission of the keyboard and hand scene is required. For this purpose, server-client communication via a QR code connection is implemented to transfer the stream between two mobile devices. Based on these deep learning technologies, a mobile web app was developed that offers 170 learning courses for touch-typing training. With the help of the Typing Learning Academy prototype, a study was conducted as part of this paper to evaluate the usability and utility of the learning app. This research demonstrates the potential for enhancing the development of writing skills through touch typing through the utilization of advanced deep learning technologies.

Web Apps with Search Engine Optimization (SEO)

Elevate your online presence with our SEO-focused web apps. Drive traffic, enhance visibility, and rank higher on search engines. Our user-friendly applications are tailored for optimal search engine optimization, ensuring maximum exposure and engagement for your website. Take control of your online success with our powerful SEO-driven web solutions.

Economic Evaluation of a Web Application Implemented in Primary Care for the Treatment of Depression in Patients With Type 2 Diabetes Mellitus: Multicenter Randomized Controlled Trial.

Depressive disorder and type 2 diabetes mellitus (T2DM) are prevalent in primary care (PC). Pharmacological treatment, despite controversy, is commonly chosen due to resource limitations and difficulties in accessing face-to-face interventions. Depression significantly impacts various aspects of a person's life, affecting adherence to medical prescriptions and glycemic control and leading to future complications and increased health care costs. To address these challenges, information and communication technologies (eg, eHealth) have been introduced, showing promise in improving treatment continuity and accessibility. However, while eHealth programs have demonstrated effectiveness in alleviating depressive symptoms, evidence regarding glycemic control remains inconclusive. This randomized controlled trial aimed to test the efficacy of a low-intensity psychological intervention via a web app for mild-moderate depressive symptoms in individuals with T2DM compared with treatment as usual (TAU) in PC. This study aimed to analyze the cost-effectiveness and cost-utility of a web-based psychological intervention to treat depressive symptomatology in people with T2DM compared with TAU in a PC setting. A multicenter randomized controlled trial was conducted with 49 patients with T2DM, depressive symptoms of moderate severity, and glycosylated hemoglobin (HbA1c) of 7.47% in PC settings. Patients were randomized to TAU (n=27) or a web-based psychological treatment group (n=22). This web-based treatment consisted of cognitive behavioral therapy, improvement of diabetes self-care behaviors, and mindfulness. Cost-effectiveness analysis for the improvement of depressive symptomatology was conducted based on reductions in 3, 5, or 50 points on the Patient Health Questionnaire-9 (PHQ-9). The efficacy of diabetes control was estimated based on a 0.5% reduction in HbA1c levels. Follow-up was performed at 3 and 6 months. The cost-utility analysis was performed based on quality-adjusted life years. Efficacy analysis showed that the web-based treatment program was more effective in improving depressive symptoms than TAU but showed only a slight improvement in HbA1c. Incremental cost-effectiveness ratios of 186.76 for a 3-point reduction in PHQ-9 and 206.31 for reductions of 5 and 50 percentage points were obtained. In contrast, the incremental cost-effectiveness ratio for improving HbA1c levels amounted to €1510.90 (€1=US $1.18 in 2018) per participant. The incremental cost-utility ratio resulted in €4119.33 per quality-adjusted life year gained. The intervention, using web-based modules incorporating cognitive behavioral therapy tools, diabetes self-care promotion, and mindfulness, effectively reduced depressive symptoms and enhanced glycemic control in patients with T2DM. Notably, it demonstrated clinical efficacy and economic efficiency. This supports the idea that eHealth interventions not only benefit patients clinically but also offer cost-effectiveness for health care systems. The study emphasizes the importance of including specific modules to enhance diabetes self-care behaviors in future web-based psychological interventions, emphasizing personalization and adaptation for this population. ClinicalTrials.gov NCT03426709; https://clinicaltrials.gov/study/NCT03426709. RR2-10.1186/S12888-019-2037-3.

Implementing no-signaling correlations as a service

We deal with no-signaling correlations that include Bell-type quantum nonlocality. We consider a logical implementation using a trusted central server with encrypted connections to clients. We show that in this way it is possible to implement two-party no-signaling correlations in an asynchronous manner. While from the point of view of physics our approach can be considered as the computer emulation of the results of measurements on entangled particles, from the software engineering point of view it introduces a primitive in communication protocols that can be capable of coordinating agents without revealing the details of their actions. We present an actual implementation in the form of a Web-based application programming interface (RESTful Web API). We demonstrate the use of the API via the simple implementation of the Clauser–Horne–Shimony–Holt game.

Computation of the Mann–Whitney Effect under Parametric Survival Copula Models

The Mann–Whitney effect is a measure for comparing survival distributions between two groups. The Mann–Whitney effect is interpreted as the probability that a randomly selected subject in a group survives longer than a randomly selected subject in the other group. Under the independence assumption of two groups, the Mann–Whitney effect can be expressed as the traditional integral formula of survival functions. However, when the survival times in two groups are not independent of each other, the traditional formula of the Mann–Whitney effect has to be modified. In this article, we propose a copula-based approach to compute the Mann–Whitney effect with parametric survival models under dependence of two groups, which may arise in the potential outcome framework. In addition, we develop a Shiny web app that can implement the proposed method via simple commands. Through a simulation study, we show the correctness of the proposed calculator. We apply the proposed methods to two real datasets.

Fast Face Recognition Based Attendance System

In recent times everything is automated by using of machine learning and AI. But in schools, colleges, some offices uses the same old traditional method, pen and paper method, for attendance, and modern facial or biometric attendance systems are very costly. We have to replace this traditional method to modern, automated, cost efficient way, and our web app is the perfect thing for this transition. It can detect your face accurately and mark the attendance by using any camera, which has to be connected to the system which is programmed to handle the face recognition

Fecal calprotectin and platelet count predict histologic disease activity in pediatric ulcerative colitis: results from a projection-predictive feature selection

Especially for pediatric patients, proxies of mucosal inflammation are needed. The Pediatric Ulcerative Colitis Activity Index (PUCAI) has been established to predict clinical and endoscopic disease activity. However, histologic inflammation might persist. We applied a special variable selection technique to predict histologic healing in pediatric ulcerative colitis (UC) as parsimoniously (but still as precisely) as possible. The retrospective analysis included data from two study cohorts, comprising 91 visits from 59 pediatric patients with UC. A Bayesian ordinal regression model was used in combination with a projection-predictive feature selection (PPFS) to identify a minimal subset of clinical and laboratory parameters sufficient for the prediction of histologic disease activity. Following the PPFS, CEDATA-GPGE patient registry data were analyzed to investigate the relevance of the selected predictors in relation to PUCAI and Physician Global Assessment (PGA) in up to 6697 patient visits. Fecal calprotectin (FC) and platelet count were identified as the minimal subset of predictors sufficient for prediction of histologic disease activity in pediatric UC. FC and platelet count also appeared to be associated with increasing disease activity as measured by PUCAI and PGA in the CEDATA-GPGE registry. Based on the selected model, predictions can be performed with a Shiny web app. Conclusion: Our statistical approach constitutes a reproducible and objective tool to select a minimal subset of the most informative parameters to predict histologic inflammation in pediatric UC. A Shiny app shows how physicians may predict the histologic activity in a user-friendly way using FC and platelet count. To generalize the findings, further prospective studies will be needed.What is Known:• Histologic healing is a major endpoint in the therapy of ulcerative colitis (UC).• The PUCAI score has been established to predict disease activity in pediatric UC but is not suitable for the prediction of histologic healing.What is New:• Our Bayesian ordinal regression model in combination with a projection-predictive feature selection is a reproducible and objective tool to select the minimal subset of clinical and laboratory parameters to predict histologic inflammation in pediatric UC.• Histologic inflammation in pediatric UC can be non-invasively predicted based on the combination of fecal calprotectin levels and platelet count.

A systematic review and meta-analysis of randomized controlled trials on the effectiveness of high-intensity laser therapy in the management of neck pain.

The purpose of this systematic review was to evaluate the effects of high-intensity laser therapy (HILT) on pain, disability, and range of movement in patients with neck pain. Randomized controlled trials (RCTs) of HILT for neck pain disorders were searched across databases such as PubMed, Web of Science, Scopus, CINAHL, Science Direct, Cochrane Library, the PEDro database, and Google Scholar (updated January 7, 2024). The main outcome was pain intensity, with neck disability and cervical range of motion as secondary outcomes. Researchers reviewed article titles and abstracts from different databases using the Rayyan web app. Study quality was assessed using the Cochrane risk of bias tool, and evidence-based recommendations were developed using the GRADE approach. A meta-analysis was conducted to calculate the pooled effect in terms of mean differences (MD) for the outcomes of interest, along with a 95% confidence interval (95% CI). Twenty studies met the selection criteria and were potentially eligible for inclusion in the meta-analysis. At the end of the treatment, there was a statistically significant (p < 0.01) pooled MD of -14.1mm for pain intensity (17 RCTs) with the VAS (95% CI:-18.4,-9.7), 3.9° (95% CI:1.9,6.7) for cervical extension (9 RCTs), and -8.3% (95% CI:-14.1,-4.1) for disability diminish (12 RCTs) with the neck disability index in favor of HILT. Only the results for pain intensity are in line with the minimal clinically important differences (MCID) reported in the literature. Overall, the evidence was deemed significant but with low certainty, attributed to observed heterogeneity and some risk of bias among the RCTs. HILT demonstrates effectiveness in reducing neck pain and disability while enhancing cervical extension when added to other physical therapy interventions, especially therapeutic exercise, based on a moderate level of evidence. This review highlights that the most favorable results are obtained when HILT is employed to address myofascial pain, cervical radiculopathy and chronic neck pain.PROSPERO registration number: CRD42023387394 (Registration date, 14/01/2023).

Development of a recommendation system and data analysis in personalized medicine: an approach towards healthy vascular ageing.

Understanding early vascular ageing has become crucial for preventing adverse cardiovascular events. To this respect, recent AI-based risk clustering models offer early detection strategies focused on healthy populations, yet their complexity limits clinical use. This work introduces a novel recommendation system embedded in a web app to assess and mitigate early vascular ageing risk, leading patients towards improved cardiovascular health. This system employs a methodology that calculates distances within multidimensional spaces and integrates cost functions to obtain personalized optimisation of recommendations. It also incorporates a classification system for determining the intensity levels of the clinical interventions. The recommendation system showed high efficiency in identifying and visualizing individuals at high risk of early vascular ageing among healthy patients. Additionally, the system corroborated its consistency and reliability in generating personalized recommendations among different levels of granularity, emphasizing its focus on moderate or low-intensity recommendations, which could improve patient adherence to the intervention. This tool might significantly aid healthcare professionals in their daily analysis, improving the prevention and management of cardiovascular diseases.

RELIABILITY AND VALIDITY OF THE REVISION HIP COMPLEXITY CLASSIFICATION

The Revision Hip Complexity Classification (RHCC) was developed by modified Delphi system in 2022 to provide a comprehensive, reproducible framework for the multidisciplinary discussion of complex revision hip surgery. The aim of this study was to assess the validity, intra-relater and inter-relater reliability of the RHCC.Radiographs and clinical vignettes of 20 consecutive patients who had undergone revision of Total Hip Arthroplasty (THA) at our unit during the previous 12-month period were provided to observers. Five observers, comprising 3 revision hip consultants, 1 hip fellow and 1 ST3-8 registrar were familiarised with the RHCC. Each revision THA case was classified on two separate occasions by each observer, with a mean time between assessments of 42.6 days (24–57). Inter-observer reliability was assessed using the Fleiss™ Kappa statistic and percentage agreement. Intra-observer reliability was assessed using the Cohen Kappa statistic. Validity was assessed using percentage agreement and Cohen Kappa comparing observers to the RHCC web-based application result.All observers were blinded to patient notes, operation notes and post-operative radiographs throughout the process.Inter-observer reliability showed fair agreement in both rounds 1 and 2 of the survey (0.296 and 0.353 respectively), with a percentage agreement of 69% and 75%.Inter-observer reliability was highest in H3-type revisions with kappa values of 0.577 and 0.441.Mean intra-observer reliability showed moderate agreement with a kappa value of 0.446 (0.369 to 0.773).Validity percentage agreement was 44% and 39% respectively, with mean kappa values of 0.125 and 0.046 representing only slight agreement.This study demonstrates that classification using the RHCC without utilisation of the web-based application is unsatisfactory, showing low validity and reliability. Reliability was higher for more complex H3-type cases. The use of the RHCC web app is recommended to ensure the accurate and reliable classification of revision THA cases.

Evaluation of reports received on a digital platform for monitoring and self-care of individuals facing the COVID-19 pandemic in Brazil: Contributions to public health

ObjectivesTo evaluate the contribution of the digital platform “Meu Diário de Quarentena (MDQ)" or My Quarantine Diary concerning the monitoring and self-care of individuals with COVID-19 in Brazil. And to analyze the epidemiological and clinical characteristics related to the disease and the users who adhered to the support provided by MDQ. MethodsMDQ was developed by a multidisciplinary team and offered to the general population to provide self-care and health education during the COVID-19 pandemic, relying on users' self-reporting of information (such as signs and symptoms, pre-existing health conditions, and medications used during quarantine). The outcomes were measured, and the web app's support experience for public health was reported. ResultsMDQ had 2439 active users on the platform, with 485 (19.9 %) self-reporting a COVID-19 diagnosis, mostly from individuals in the southeastern region of Brazil (56.5 %). The most common pre-existing health condition reported was related to circulatory system diseases. The most frequent reported signs and symptoms included headache, cough, myalgia, nasal congestion and muscle weakness. Corticosteroids, multivitamins, and anti-inflammatories were the most used medications during the pandemic period. There were several reports related to how users were feeling during the pandemic, and among these reports, negative feelings toward isolation stood out, such as “feeling lonely”, “anxious”, and “feeling useless”. A significant association was found between sex (p < 0.001) and age (p < 0.001) in relation to self-reported cases of COVID-19. ConclusionsThe use of MDQ during extended quarantine was an easy and interesting way of interaction and support for people during COVID-19 pandemic.

Development of the Software System for Managing a Digital Pet ID

Recent Research and Publications Analysis: The shift towards digital documentation, such as Ukraine's «Diia» for human records, has not yet been fully embraced in pet care, creating a significant service gap. Ukraine, with a high number of household pets, especially approximately 7.63 million cats, highlights the need for a comprehensive digital pet management system. Given the frequent cases of pets getting lost—with low recovery rates—a robust digital system is essential for improving these figures and enhancing pet safety. When designing software, it is important to choose the right technologies for both the web interface and the backend. Django is recommended for the backend because of its «batteries-included» architecture, which provides a comprehensive set of ready-to-use tools that facilitate rapid development and ensure a high level of security. For the inter-face, it is recommended to use JavaScript integrated with frameworks such as React, An-gular or Vue to create dynamic applications that improve the user experience with asyn-chronous requests, allowing the content of the page to be updated without reloading the page. This combination not only provides scalability and security, but also effectively meets the complex needs of web applications. Purpose of the Study. This study aims to develop a software system that facilitates the management of digital pet IDs, which will integrate medical records, vaccination his-tories, and detailed activity logs. This integration aims to streamline pet care, making it more efficient and significantly more convenient for pet owners. Main Material Presentation. The proposed system's architecture will include: – backend. Utilizing Django REST Framework for creating scalable, secure web APIs that handle data operations efficiently; – frontend. Employing JavaScript, HTML, and CSS to provide a responsive and in-teractive user experience. Key Features: – digital passports for pets, verifiable via QR codes; - detailed activity logs that track and display pet movements and behaviors; – comprehensive vaccination records accessible by both pet owners and veterinari-ans; – a lost pet bulletin board that uses geographical data to notify users of nearby lost or found pets. Conclusions.Technologies have been chosen and a software system has been devel-oped for effective management of digital pet IDs, integrating key functions for compre-hensive data management of pets. It utilizes modern technologies to ensure reliable data security, high scalability, and enhanced user interaction, making it a key achievement in the management of digital pet IDs.

FEBIAD ionization development via a web-app for multidimensional characterization

The ISAC-FEBIAD is an electron impact ion source typically used to ionize radioactive molecules or isotopes of elements beyond the reach of either surface or laser ion sources. The FEBIAD’s key tuning parameters are the cathode temperature defining the number of electrons created; the anode voltage establishing the electron energy; and the magnetic field controlling the electron density inside the anode volume. However, these parameters are typically scanned in a small and limited range when optimizing the source. Recent investigations have shown the need to explore the entire range of operational values accessible by the power supplies, not only due to the intrinsic variations from source to source but also to operate the source at optimal settings. To address this, a scanning algorithm has been implemented as a web interface thanks to the High-Level-Application (HLA) infrastructure available at TRIUMF. The ion beam intensity during both offline and online commissioning of the web app are presented here as contour plots. The optimal settings found for stable 20Ne are confirmed as the optimal settings for radioactive 18Ne. The main takeaway, however, is that the optimal ion source parameters differ between singly-charged, doubly-charged, and molecular species. This development demonstrate and facilitate the need for element and charge state-specific parameter optimization. Additionally, the results highlight the possibility of parameter optimization to enhance the ratio of the species of interest to co-ionized contamination.

Python and Plotly Dash, A Quick and Convenient Way to Develop Web Apps for Teaching Physical Chemistry Models

Python and Plotly Dash, A Quick and Convenient Way to Develop Web Apps for Teaching Physical Chemistry Models

A CRITICAL EVALUATION OF SECURITY APPROACHES FOR DETECTION AND PREVENTION OF SQL INJECTION ATTACKS IN WEB-BASED APPLICATIONS

SQL Injection Attack (SQLIAs) is a web application attack that has been known for almost two decades, and that has been among the biggest cyber threats especially because most of the world’s population interacts with web apps in one way or the other. Over the years many methods have been developed to identify and deter SQLIAs, thereby reducing the risk on web applications. Four various methods used to identify and stop SQLIAs are reviewed, compared and critically evaluated in this paper, these include tokenization and lexicon detection process, combined static and dynamic method, novel, and search-based methods. This work further reveals the gap in current knowledge, specifically, increased efficiency can be achieved by integrating two of the most effective approaches. Furthermore, a real-world application of these methods is presented and finally, recommendations are made for further study.

Guided web app intervention for reducing symptoms of depression in postpartum women: Results of a feasibility randomized controlled trial

BackgroundChile faces a significant postpartum depression prevalence and treatment gap, necessitating accessible interventions. While cognitive-behavioral internet-based interventions have proven effective in high-income countries, this field is underdeveloped in Chile. Based on the country's widespread use of digital technology, a guided 8-week cognitive-behavioral web app intervention named “Mamá, te entiendo” was developed. ObjectiveThis study aimed to assess the acceptability and feasibility of “Mamá, te entiendo”, for reducing depressive symptomatology in postpartum women. MethodsSixty-five postpartum women with minor or major depression were randomly assigned to either intervention or waitlist. Primary outcomes centered on study feasibility, intervention feasibility, and acceptability. Semi-structured interviews with a sub-sample enriched the understanding of participants' experiences. Secondary outcomes included mental health variables assessed at baseline, post-intervention, and 1-month follow-up. ResultsChilean women displayed great interest in the intervention. 44.8 % of participants completed the intervention. Participants reported high satisfaction and engagement levels, with interviewees highlighting the value of the intervention's content, exercises, and therapist's feedback. However, preliminary efficacy analysis didn't reveal a significant interaction between group and time for outcome measures. DiscussionThis research represents a pioneering effort in Chile to evaluate an internet-based intervention for postpartum depression symptoms. The demonstrated feasibility and acceptability highlight the potential of integrating technology-driven approaches into mental health interventions. However, the intervention did not demonstrate superiority, as both groups exhibited similar positive progress in several outcomes. Therefore, the following research phase should involve a larger and more diverse sample to assess the intervention's effectiveness, identify influencing factors, and determine the individuals who benefit the most.

DETECTA – MULTIPLE DISEASE DETECTION

Machine Learning Techniques for Predictive Analytics in Healthcare There are multiple techniques in machine learning that can in a variety of industries, do predictive analytics on large amounts of data. Predictive analytics in healthcare is a difficult endeavor, but it can eventually assist practitioners in making timely decisions regarding patients' health and treatment based on massive data. Diseases like Breast cancer, diabetes, and heart-related diseases are causing many deaths globally but most of these deaths are due to the lack of timely check-ups of the diseases. The above problem occurs due to a lack of medical infrastructure and a low ratio of doctors to the population. The statistics clearly show the same, WHO recommended, the ratio of doctors to patients is 1:1000 whereas India's doctor-to- population ratio is 1:1456, this indicates the shortage of doctors. The diseases related to heart, cancer, and diabetes can cause a potential threat to mankind, if not found early. Therefore, early recognition and diagnosis of these diseases can save a lot of lives. This work is all about predicting diseases that are harmful using machine learning classification algorithms. In this work, breast cancer, heart, and diabetes are included. To make this work seamless and usable by the mass public, our team made a medical test web application that makes predictions about various diseases using the concept of machine learning. In this work, our aim to develop a disease-predicting web app that uses the concept of machine learning-based predictions about various diseases like Breast cancer, Diabetes, Heart diseases, Covid, Pneumonia, Alzheimer.

CO2 Emission Compensation by Tree Species in Some Urban Green Areas

Mitigating the negative impacts of climate change in urban areas has recently become essential to improving citizens’ living conditions. Trees are one of the most effective ways to attenuate the Heat Island phenomenon in cities, and numerous projects have been carried out to calculate tree ecosystem services (ES) provisioning. Among these, the Clivut European project (LIFE 18 GIC/IT/001217) developed a web app to allow citizens and the public administration to quantify the ES provided by the most common tree species. The present study aims to consider a new model to calculate the tree evapotranspiration cooling effect in the urban environment in terms of CO2-compensated emissions. The model directly converts the surface temperature change produced by tree evapotranspiration into the corresponding CO2 offset in four urban parks in two Italian cities (Bologna and Perugia). The considered parks stored 1100 t of CO2 at the time of the study, while the CO2 compensated is 860 t, showing the significance of this interpretation. As a result of the study, it can be concluded that the presented model will allow a better estimation of the potential trees’ climate change compensation and also add further functionality to the web app.

Empowering Potential of the My Assistive Technology Guide: Exploring Experiences and User Perspectives.

The use of assistive technology (AT) devices enhances older adults' function in daily activities. However, the lack of awareness of AT among potential AT users has been identified as a major barrier to its adoption. This study aimed to assess the quality of the Mi Guía de Asistencia Tecnológica (MGAT) web app, which provides information on AT, from the perspective of older Latinos with physical disabilities, and to explore their experience using the MGAT. We employed a convergent parallel mixed-method design involving 12 older Latinos living in Puerto Rico. In Phase I, the researchers trained the participants in the use of the MGAT. In Phase II, participants were encouraged to use it for 30 days. In Phase III, the participants completed the User Mobile Application Rating Scale and individual interviews, analyzed with descriptive statistics and a directed thematic content analysis. The quality of the MGAT was rated high in both the objective (mean = 3.99; SD = 0.7) and subjective (mean = 4.13; SD = 1.1) domains. Qualitative data revealed the MGAT was accessible, usable, desirable, credible, useful, and valuable to increasing older Latinos' AT knowledge, function, and autonomy. The MGAT has the potential to increase AT awareness and adoption among older adults.

Whatsapp Chat Analyzer Using Machine Learning

WhatsApp has emerged as the go-to method for communication. Conversations on WhatsApp cover a wide range of topics among individuals or groups. This data can be valuable for advancing technologies like machine learning, which rely on quality data for effective learning experiences. Our tool is designed to offer comprehensive analysis of WhatsApp data, regardless of the subject of the conversation. By using our developed code, a deeper insight into the data can be achieved. One great benefit of this tool is that it utilizes common Python libraries like Pandas, Matplotlib, Seaborn, Streamlit, Numpy, Re, Emojis, and sentiment analysis to generate data frames and visualizations. These are then showcased in a streamlit web app that is efficient and requires fewer resources. This makes it ideal for analyzing large datasets. Key Words: Inspecting, Examining, Research, Data Analysis, Matplotlib, Pandas, Streamlit